Training in progress, step 500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d7ea76a7fe9a3a72bfd9d91b402405835199ee3276e58a75b2b90de4df6faf3
+oid sha256:f1ae0cef03350b13f2142034ec12a4f632f2a167671a45fb33d96be882bf8881
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55accac051f9670b17e34e185dbc7868d482bf70ed6d173806a6b70a0e363569
+oid sha256:b4e7bc77588b6383613b88b55c7bb31c785abbac487d86ed9e1ea0688d925796
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:470231bc1b9887c06a948023513b621d90c9fafd020c42706547857cecbea47a
+oid sha256:86bc4ba66dd9b2678296e8603b5fc45b9513c8a929966cabd3603650c1d00ca8
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f6c57457d54b7bbc2f9492e8a647b031ace734fd264dd50bf21159a960787c9
+oid sha256:b7ddf240f6d195d0e03799bc56610ed87dcf151c18d11e02b13b1a13f27c3bac
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c43ae2edd3b792abc4b0bbe5b96b0cbff30dfd7f8da70e732cd4ef7bf6a1ef4a
+oid sha256:628e045b78e5d559e9fcef6658ed03e911773af6f7354bf6b3b679b0ff34bfdb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 36.92307692307692,
+  "epoch": 38.46153846153846,
   "eval_steps": 40,
-  "global_step": 480,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -447,6 +447,20 @@
       "eval_samples_per_second": 284.308,
       "eval_steps_per_second": 4.546,
       "step": 480
+    },
+    {
+      "epoch": 37.69230769230769,
+      "grad_norm": 0.4140625,
+      "learning_rate": 1.7822218477475494e-05,
+      "loss": 9.1778,
+      "step": 490
+    },
+    {
+      "epoch": 38.46153846153846,
+      "grad_norm": 0.419921875,
+      "learning_rate": 1.4808059116167305e-05,
+      "loss": 9.1781,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -466,7 +480,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 196396103761920.0,
+  "total_flos": 204579274752000.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null